NetEase Youdao open-sources Confucius4-R2T2, a 1.7B real-time streaming ASR model for voice agents
_akhaliq · x · 2026-09-18
NetEase Youdao has open-sourced Confucius4-R2T2, a 1.7B-parameter true streaming ASR model built for voice agents.
Key points:
- Fine-grained, configurable decoding chunks from 80ms to 2s, delivering low latency and high accuracy
- Append-only output mode: transcript text is committed permanently without revising previous words, avoiding flickering and disruptive rewrites in real-time UIs
- Targets live captioning, downstream NLP/LLM agent pipelines, and simultaneous speech translation
Code and weights are available on GitHub and Hugging Face, with WebSocket server/client examples included.
Related event: NetEase Youdao Open-Sources Confucius4-R2T2 Real-Time Streaming ASR(21 posts)→
More from Models
- Ternary-Bonsai-2-27B 2-bit MLX quantized model trends on Hugging Face — prism-ml · 2026-09-18
- User burns through ChatGPT Pro weekly quota in 2 days running Codex — craigbalding · 2026-09-18
- Users speculate Gemini 4 training as Gemini 3.8 Flash slows on Antigravity — haider1 · 2026-09-18
- Dev swapped to Opus 5 after OpenAI credits ran out — 'this is not great' — lucasmeijer · 2026-09-18
- 234 Days Later: Opus-Class Intelligence Runs Locally on a Single 8GB RTX 3060 — JFPuget · 2026-09-18
- Dev's daily-driver LLM stack: GLM, DeepSeek and Qwen now rival closed models — Jasonio · 2026-09-18